YellowFin

2000년 도입 · 논문 1편에서 사용

YellowFin is a learning rate and momentum tuner motivated by robustness properties and analysis of quadratic objectives. It stems from a known but obscure fact: the momentum operator's spectral radius is constant in a large subset of the hyperparameter space. For quadratic objectives, the optimizer tunes both the learning rate and the momentum to keep the hyperparameters within a region in which the convergence rate is a constant rate equal to the root momentum. This notion is extended empirically to non-convex objectives. On every iteration, YellowFin optimizes the hyperparameters to minimize a local quadratic optimization.

출처: YellowFin and the Art of Momentum Tuning

소개 논문: YellowFin and the Art of Momentum Tuning